Llama 4 - a DevQuasar Collection

DevQuasar 's Collections

Nvidia reward models GGUF

Very Large GGUFs

Llama 4

Nvidia AceInstruct and AceMath

HuggingFaceTB.finemath GUFFs

IBM Granite3.1 GGUF

tiiuae Falcon3 GGUF

Analytical Reasoning

IBM Granite3 GGUF

GGUFs

Llama 4

updated Apr 9, 2025

DevQuasar/meta-llama.Llama-4-Maverick-17B-128E-Instruct-GGUF

Text Generation • 401B • Updated Apr 18, 2025 • 90
DevQuasar/meta-llama.Llama-4-Scout-17B-16E-Instruct-GGUF

Text Generation • 108B • Updated Apr 11, 2025 • 101 • 3